Machine Unlearning (MU) aims to remove the influence of specific knowledge from a pretrained model. Existing methods often rely on retained training data to preserve utility; such dependence is impractical due to privacy and scalability constraints. A further complication arises when unlearning is applied to vision-language models (VLMs), where entangled multimodal representations make targeted forgetting especially challenging. We propose DIET, a principled retain-data-free unlearning method for VLMs that addresses these challenges by leveraging the geometry of hyperbolic space. The core idea is to push forget embeddings toward class-mismatched prototypes located at the boundary of the hyperbolic space. In hyperbolic geometry, points near the boundary become infinitely distant from interior points. As a result, moving forget embeddings to the boundary makes their influence on the model asymptotically negligible. To formalize this, we guide the forgetting process using the Busemann function, which quantifies directional distance to the boundary. We further develop an adaptive scheme based on optimal transport that selects mismatched prototypes for each forget embedding, enabling flexible unlearning dynamics. Extensive experiments on fine-grained datasets such as Flowers102, OxfordPets, and StanfordCars show that DIET achieves an average forget accuracy of 8.06%, while preserving 69.04% utility using only 16 samples per concept, significantly outperforming the best retain-free baselines with a 117.5% improvement in model utility, and showing competitive performance to retain-data baselines with only a 3.79% drop

Diffusion models are highly effective at generating high-quality images but pose risks, such as the unintentional generation of NSFW (not safe for work) content. Although various techniques have been proposed to mitigate unwanted influences in diffusion models while preserving overall performance, achieving a balance between these goals remains challenging. In this work, we introduce EraseDiff, an algorithm designed to preserve the utility of the diffusion model on retained data while removing the unwanted information associated with the data to be forgotten. Our approach formulates this task as a constrained optimization problem using the value function, resulting in a natural first-order algorithm for solving the optimization problem. By altering the generative process to deviate away from the groundtruth denoising trajectory, we update parameters for preservation while controlling constraint reduction to ensure effective erasure, striking an optimal trade-off. Extensive experiments and thorough comparisons with state-of-the-art algorithms demonstrate that EraseDiff effectively preserves the model’s utility, efficacy, and efficiency.$\color{Red} {\text {WARNING}}$: This paper contains sexually explicit imagery that may be offensive in nature.

Machine Unlearning (MU) aims to selectively erase harmful behaviors from models while retaining the overall utility of the model. As a multi-task learning problem, MU involves balancing objectives related to forgetting specific concepts/data and preserving general performance. A naive integration of these forgetting and preserving objectives can lead to gradient conflicts and dominance, impeding MU algorithms from reaching optimal solutions. To address the gradient conflict and dominance issue, we reformulate MU as a two-player cooperative game, where the two players, namely, the forgetting player and the preservation player, contribute via their gradient proposals to maximize their overall gain and balance their contributions. To this end, inspired by the Nash bargaining theory, we derive a closed-form solution to guide the model toward the Pareto stationary point. Our formulation of MU guarantees an equilibrium solution, where any deviation from the final state would lead to a reduction in the overall objectives for both players, ensuring optimality in each objective. We evaluate our algorithm's effectiveness on a diverse set of tasks across image classification and image generation. Extensive experiments with ResNet, vision-language model CLIP, and text-to-image diffusion models demonstrate that our method outperforms state-of-the-art MU algorithms, achieving a better trade-off between forgetting and preserving. Our results also highlight improvements in forgetting precision, preservation of generalization, and robustness against adversarial attacks.

Federated Learning (FL) is a distributed learning paradigm that enhances users' privacy by eliminating the need for clients to share raw, private data with the server. Despite the success, recent studies expose the vulnerability of FL to model inversion attacks, where adversaries reconstruct users’ private data via eavesdropping on the shared gradient information. We hypothesize that a key factor in the success of such attacks is the low entanglement among gradients per data within the batch during stochastic optimization. This creates a vulnerability that an adversary can exploit to reconstruct the sensitive data. Building upon this insight, we present a simple, yet effective defense strategy that obfuscates the gradients of the sensitive data with concealed samples. To achieve this, we propose synthesizing concealed samples to mimic the sensitive data at the gradient level while ensuring their visual dissimilarity from the actual sensitive data. Compared to the previous art, our empirical evaluations suggest that the proposed technique provides the strongest protection while simultaneously maintaining the FL performance. Code is located at https://github.com/JingWu321/DCS-2.

Numerous mobile apps have leveraged deep learning capabilities. However, on-device models are vulnerable to attacks as they can be easily extracted from their corresponding mobile apps. Although the structure and parameters information of these models can be accessed, existing on-device attacking approaches only generate black-box attacks (i.e., indirect white-box attacks), which are less effective and efficient than white-box strategies. This is because mobile deep learning (DL) frameworks like TensorFlow Lite (TFLite) do not support gradient computing (referred to as non-debuggable models), which is necessary for white-box attacking algorithms. Thus, we argue that existing findings may underestimate the harm-fulness of on-device attacks. To validate this, we systematically analyze the difficulties of transforming the on-device model to its debuggable version and propose a Reverse Engineering framework for On-device Models (REOM), which automatically reverses the compiled on-device TFLite model to its debuggable version, enabling attackers to launch white-box attacks. Our empirical results show that our approach is effective in achieving automated transformation (i.e., 92.6%) among 244 TFLite models. Compared with previous attacks using surrogate models, REOM enables attackers to achieve higher attack success rates (10.23%→89.03%) with a hundred times smaller attack perturbations (1.0→0.01). Our findings emphasize the need for developers to carefully consider their model deployment strategies, and use white-box methods to evaluate the vulnerability of on-device models. Our artifacts 1 are available.

More and more edge devices and mobile apps are leveraging deep learning (DL) capabilities. Deploying such models on devices – referred to as on-device models – rather than as remote cloud-hosted services, has gained popularity because it avoids transmitting user’s data off of the device and achieves high response time. However, on-device models can be easily attacked, as they can be accessed by unpacking corresponding apps and the model is fully exposed to attackers. Recent studies show that attackers can easily generate white-box-like attacks for an on-device model or even inverse its training data. To protect on-device models from white-box attacks, we propose a novel technique called model obfuscation. Specifically, model obfuscation hides and obfuscates the key information – structure, parameters and attributes – of models by renaming, parameter encapsulation, neural structure obfuscation, shortcut injection, and extra layer injection. We have developed a prototype tool ModelObfuscator to automatically obfuscate on-device TFLite models. Our experiments show that this proposed approach can dramatically improve model security by significantly increasing the difficulty of parsing models’ inner information, without increasing the latency of DL models. Our proposed on-device model obfuscation has the potential to be a fundamental technique for on-device model deployment. Our prototype tool is publicly available at https://github.com/zhoumingyi/ModelObfuscator.

Machine learning models are vulnerable to adversarial examples. For the black-box setting, current substitute attacks need pre-trained models to generate adversarial examples. However, pre-trained models are hard to obtain in real-world tasks. In this paper, we propose a data-free substitute training method (DaST) to obtain substitute models for adversarial black-box attacks without the requirement of any real data. To achieve this, DaST utilizes specially designed generative adversarial networks (GANs) to train the substitute models. In particular, we design a multi-branch architecture and label-control loss for the generative model to deal with the uneven distribution of synthetic samples. The substitute model is then trained by the synthetic samples generated by the generative model, which are labeled by the attacked model subsequently. The experiments demonstrate the substitute models produced by DaST can achieve competitive performance compared with the baseline models which are trained by the same train set with attacked models. Additionally, to evaluate the practicability of the proposed method on the real-world task, we attack an online machine learning model on the Microsoft Azure platform. The remote model misclassifies 98.35% of the adversarial examples crafted by our method. To the best of our knowledge, we are the first to train a substitute model for adversarial attacks without any real data.